# sweetice/Deep-reinforcement-learning-with-pytorch

PyTorch implementation of DQN, AC,  ACER, A2C, A3C, PG,  DDPG, TRPO, PPO, SAC, TD3 and ....

Repository: https://github.com/sweetice/Deep-reinforcement-learning-with-pytorch
Canonical: https://ross.abutalabs.com/products/deep-reinforcement-learning-with-pytorch
Language: Python
License: MIT
License Family: permissive
Topics: policy-gradient, pytorch, actor-critic-algorithm, alphago, deep-reinforcement-learning, a2c, dqn, sarsa, ppo, a3c, resnet, algorithm, deep-learning, reinforce, actor-critic, sac, td3, trpo
Last push: 2023-03-24T23:36:09+00:00

## Health v2 (maintenance only)
Score: 32/100 (v2, computed 2026-09-03T02:20:16.233290+00:00)
- activity 0, release rhythm 35, longevity 100
- inputs: {"age_days": 3008, "days_push": 1258, "days_rel": null, "gap_med": null, "n_releases_24m": 0}
- flags: no_releases
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 4651, forks 895 (observed 2026-08-28T04:08:55.628839+00:00)

## What it is
A collection of clear PyTorch implementations of classic and state-of-the-art deep reinforcement learning algorithms such as DQN, A3C, PPO, SAC, TD3, and TRPO. It is designed as an educational resource for people learning deep RL algorithms.

## Use cases
- learn deep reinforcement learning algorithms with pytorch
- study dqn implementation on cartpole
- understand ppo and sac algorithm code
- reference implementations of actor-critic methods
- compare policy gradient algorithms side by side
- run td3 on bipedalwalker

## When to choose
- you want readable educational implementations of RL algorithms
- you are learning deep RL and want to read clean pytorch code
- you need reference code for DQN, PPO, SAC, TD3, or related algorithms

## When to avoid
- you need a production-ready or well-maintained RL framework
- you require modern Python versions or up-to-date dependencies
- you need a stable API for training RL agents at scale

## Facets
- artifact type: learning-resource
- maturity: maintenance
- function: reinforcement-learning, machine-learning, deep-learning
- domain: reinforcement-learning, machine-learning, deep-learning, tutorials
- platform: python, cross-platform
- tags: pytorch, dqn, ppo, actor-critic, sac, td3, a3c, ddpg, trpo, policy-gradient, educational

## Member repositories
- sweetice/Deep-reinforcement-learning-with-pytorch (main) score 32

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:08:55.628839+00:00.
- Health v2: computed from the inputs above; adoption is never an input.
- Inferred fields (summary, facets, guidance): AI-extracted, prompt v1, taxonomy v1, on 2026-08-29T18:19:30.095603+00:00, confidence not recorded.
  - readme: https://github.com/sweetice/Deep-reinforcement-learning-with-pytorch (fetched 2026-08-28T04:08:55.628839+00:00, sha 84317356f54a)
- Data as of 2026-08-30T08:39:29.467469+00:00.